NM Testing

company

AI & ML interests

None defined yet.

Recent Activity

nm-autobot updated a model about 1 hour ago

nm-testing/w4a16_moe-e2e

nm-autobot updated a model about 2 hours ago

nm-testing/Qwen3-30B-A3B-NVFP4-AWQ-e2e

nm-autobot updated a model about 2 hours ago

nm-testing/w8a8_static_asym-e2e

View all activity

nm-testing 's models 555

nm-testing/tinyllama-oneshot-w8-channel-a8-tensor

Text Generation • 1B • Updated Aug 20 • 1.34k

nm-testing/tinyllama-oneshot-w4a16-group128-v2

Text Generation • 1B • Updated Aug 20 • 3.52k

nm-testing/tinyllama-oneshot-w4a16-channel-v2

Text Generation • 1B • Updated Aug 20 • 5.64k • 1

nm-testing/tinyllama-one-shot-w4a16-group-packed

Text Generation • 1B • Updated Aug 20 • 88

nm-testing/tinyllama-marlin24-w4a16-group128

Text Generation • 0.3B • Updated Aug 20 • 86

nm-testing/nonuniform

Text Generation • 8B • Updated Aug 20 • 76

nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt

Text Generation • 0.9B • Updated Aug 20 • 77

nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t

Text Generation • 1B • Updated Aug 20 • 226 • 1

nm-testing/llama3-8b-w8_channel-a8_tensor-compressed

Text Generation • 8B • Updated Aug 20 • 92

nm-testing/llama-3-instruct-w8a8-dyn-per-token-test

Text Generation • 8B • Updated Aug 20 • 75

nm-testing/granite-8b-code-instruct-128k2of4-W8A8-FP8-Dynamic-Per-Token

8B • Updated Aug 20 • 21

nm-testing/granite-3.1-8b-instruct2of4-W8A8-FP8-Dynamic-Per-Token

8B • Updated Aug 20 • 14

nm-testing/TinyLlama-1.1B-Chat-v1.0-kvcache-fp8-tensor

1B • Updated Aug 20 • 1.44k

nm-testing/TinyLlama-1.1B-Chat-v1.0-kvcache-fp8-attn_head

1B • Updated Aug 20 • 1.24k

nm-testing/TinyLlama-1.1B-Chat-v1.0-kv_cache_default_tinyllama-e2e

1B • Updated Aug 20 • 11

nm-testing/SmolLM-360M-Instruct-quantized.w4a16

0.4B • Updated Aug 20 • 13

nm-testing/SmolLM-135M-Instruct-quantized.w4a16

Text Generation • 0.2B • Updated Aug 20 • 95

nm-testing/Qwen2-1.5B-Instruct-FP8W8

Text Generation • 2B • Updated Aug 20 • 1.03k

nm-testing/Qwen2-0.5B-Instruct

Text Generation • 0.6B • Updated Aug 20 • 75

nm-testing/Phi-3-mini-4k-instruct-kv_cache_default_phi3-e2e

4B • Updated Aug 20 • 11

nm-testing/Phi-3-mini-128k-instruct-FP8

4B • Updated Aug 20 • 1.37k

nm-testing/Mixtral-8x7B-Instruct-v0.1-W4A16-quantized

47B • Updated Aug 20 • 25

nm-testing/Mixtral-8x7B-Instruct-v0.1-W4A16-channel-quantized

47B • Updated Aug 20 • 20

nm-testing/Mixtral-8x7B-Instruct-v0.1-FP8-quantized

47B • Updated Aug 20 • 6

nm-testing/Mistral-7B-Instruct-v0.32of4-W8A8-FP8-Dynamic-Per-Token

7B • Updated Aug 20 • 14

nm-testing/Meta-llama3-8b-Instruct-quant-FP8

Text Generation • 8B • Updated Aug 20 • 20

nm-testing/Meta-llama3-8b-Instruct-SmoothQuant-Fp8

Text Generation • 8B • Updated Aug 20 • 75

nm-testing/Meta-Llama-3.1-8B-Instruct-FP8-hf

Text Generation • 8B • Updated Aug 20 • 87

nm-testing/Meta-Llama-3-8B-Instruct-spinquantR3-FP8_asym-attn

8B • Updated Aug 20 • 11

nm-testing/Meta-Llama-3-8B-Instruct-nonuniform-test

Text Generation • 8B • Updated Aug 20 • 6.35k